AI Model Watch
Models / Alibaba

Qwen-Turbo

Deprecated

DEPRECATED, and scheduled for DECOMMISSIONING 2026-10-10 00:00:00 (UTC+08) in the Beijing and Singapore regions per Alibaba service notice id=1841 ("Notice on the Decommissioning of Certain Historical Mainline Models", published 2026-04-13), which names qwen-turbo, qwen-vl-max, qwen-vl-plus, qwq-plus and qvq-max as plain text. CORRECTED 2026-09-08: this row previously read "no end-of-service date published, still callable" and left retires_on null. That was our omission, not a provider change — the notice predates our 2026-06-28 backfill by ten weeks — so no changelog event. Pricing and the replacement pointer still come from https://www.alibabacloud.com/help/en/model-studio/model-pricing, which states verbatim: "Qwen-Turbo will no longer be updated. We recommend switching to Qwen-Flash."; notice id=1841 recommends only "the latest Qwen3.6/Qwen3.7 series models" generically, so replacement is kept at the pricing page's named target. Alias = qwen-turbo-2025-04-28. Official International price: $0.05 in; output $0.2 (Non-Thinking) / $0.5 (Thinking) per 1M. Older snapshot qwen-turbo-2024-09-19 -> replacement qwen-flash-2025-07-28. deprecated_on left null: Alibaba publishes a decommissioning date for this model, not a dated deprecation announcement. Text-only.

Qwen-Turbo by Alibaba costs $0.05 per 1M input tokens and $0.2 per 1M output tokens ($0.088/1M blended), with a 1M (1.000.000-token) context window. It is deprecated, shutting down 10 Oct 2026; the recommended replacement is Qwen-Flash.

Last verified: 26 Sep 2026 · sourced from official provider documentation

Retires on 10 Oct 2026

Lifecycle warning

This model is deprecated. Recommended migration: Qwen-Flash.

Read the Qwen-Turbo migration guide → replacement & cheapest alternatives

Provider
Alibaba
Status
Deprecated
Input price
$0.05 / 1M tokens
Output price
$0.2 / 1M tokens
Cached input
—
Blended price
$0.088 / 1M tokens
Context window
1.000.000 tokens (1M)
Max output
—
Modality
text
Open weights
No — API only
Knowledge cutoff
—
Released
28 Apr 2025
API string
qwen-turbo

Source: Alibaba official documentation ↗

See also

Explore more

All Alibaba models→

Prices, context windows and lifecycle status for every Alibaba model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Qwen-Turbo — questions & answers

How much does Qwen-Turbo cost?

Qwen-Turbo is priced at $0.05 per 1M input tokens and $0.2 per 1M output tokens ($0.088/1M blended at a 3:1 input-to-output ratio).

What is the context window of Qwen-Turbo?

Qwen-Turbo has a 1.000.000-token context window (1M).

Is Qwen-Turbo being deprecated or retired?

Qwen-Turbo is deprecated. Its scheduled shutdown date is 10 Oct 2026. The recommended migration is Qwen-Flash.

Does Qwen-Turbo support image or vision input?

Our catalog lists Qwen-Turbo's modalities as text; image/vision input is not among them.

Can I self-host Qwen-Turbo?

No — Qwen-Turbo is proprietary. Its weights are not publicly released, so it is available only through Alibaba's API (or hosted partners), not for self-hosting.

What is the API model string for Qwen-Turbo?

The API model identifier for Qwen-Turbo is "qwen-turbo" when calling Alibaba's API.